[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-327628-105":59,"doc-detail-327628-en":131},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":124,"head_meta":126,"extra_data":128,"updated_unix":130},105,"en","the-foreign-policy-ai-evaluation-gap","The Foreign Policy AI Evaluation Gap","","AI systems used in foreign policy tasks should be a priority test case for technical AI governance because standard evaluation practices struggle in high-consequence statecraft. The paper defines statecraft as institutionally mediated formulation and implementation of external objectives and highlights structural challenges: partial observability, unbounded action spaces, contested ground truth, and multidimensional objectives. It proposes a literature-grounded agenda with an ecosystem review and a demand-side framework for decomposing workflows into bounded, evaluable sub-tasks.",{"@graph":69,"@context":123},[70,84,106],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/the-foreign-policy-ai-evaluation-gap/327628/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/the-foreign-policy-ai-evaluation-gap/327628.png","ImageObject",300,407,{"name":92,"@type":93},"Aria","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-11-13","2026-09-21",true,{"@type":102,"interactionType":103,"userInteractionCount":105},"InteractionCounter",{"@type":104},"ViewAction",15,{"@type":107,"mainEntity":108},"FAQPage",[109,115,119],{"name":110,"@type":111,"acceptedAnswer":112},"Why is foreign policy a priority domain for AI evaluation in technical AI governance research?","Question",{"text":113,"@type":114},"Because foreign policy/statecraft is high-consequence and structurally hard to evaluate, with conditions like partial observability, unbounded action spaces, contested ground truth, and multidimensional objectives that standard benchmark practices handle poorly.","Answer",{"name":116,"@type":111,"acceptedAnswer":117},"How does the paper define statecraft in the context of foreign policy AI systems?",{"text":118,"@type":114},"Statecraft refers to the purposive, institutionally mediated conduct through which political actors formulate and implement external objectives, including diplomacy, negotiations, sanctions, crisis response, and the use of force.",{"name":120,"@type":111,"acceptedAnswer":121},"What is the main proposal for improving evaluation of AI systems in foreign-policy workflows?",{"text":122,"@type":114},"The paper advocates a demand-side evaluation framework that decomposes foreign-policy workflows into bounded, evaluable sub-tasks, combined by humans under institutional and strategic constraints.","https://schema.org",{"og:url":83,"og:type":125,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":127,"canonical":83},"index,follow",{"doc_id":129,"site_id":62},327628,1790450974,{"code":4,"msg":5,"data":132},{"doc_id":129,"user_id":133,"nickname":92,"user_avatar":134,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":135,"file_id":136,"file_url":137,"file_type":138,"file_size":139,"view_count":105,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":140,"language":141,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":142,"faqs":143,"seo_title":144,"seo_description":67,"update_tm":145,"read_time":146,"preview_page_count":4},2336464648322,"https://ap-avatar.wpscdn.com/avatar/2200025388227c56fec?_k=1778556882303663488","The Foreign Policy AI Evaluation Gap  \nCharles Pozniak * 1 Jeba Sania * 1  \narXiv :2607 .02955v 1 [ cs .CY] 3 Jul 2026  \nAbstract  \nWe argue that AI systems used in conducting foreign policy tasks –– broadly enacting ’statecraft’  \n– should be a priority test case for technical AI governance research. In enacting foreign policy, we refer to the formulation and implementation of external objectives by political actors. Statecraft is a high-consequence deployment domain, with extreme downside risks and structural properties that standard evaluation practices handle poorly. These features include partial observability, unbounded action spaces, contested ground truth, and multidimensional objectives. This paper advocates for a literature-grounded research agenda. Our contribution is threefold: (i) a claim about the structural conditions of foreign policy that combine catastrophic tail risk with technical evaluation complexities,(ii) an ECOSYSTEM review that highlights the asymmetric focus on ASSESSMENT features over ACCESS, VERIFICATION, SECURITY, and OPERATIONALIZATION, and (iii) a demand-side evaluation framework that decomposes foreign-policy workflows into bounded, evaluable sub-tasks with human recombination. As AI systems are already being deployed in the conduct of war and peace, amid limited public evaluation infrastructure from the technical AI governance community, this agenda is an urgent priority.  \n1. Introduction  \nAI systems have already entered foreign-policy workflows before the technical AI governance community has built evaluation infrastructure for them. Many initial uses appear administrative, but LLM systems are increasingly being explored for analysis, planning, and decision-support functions  \n1Belfer Center, Harvard Kennedy School, Cambridge, MA, USA. Correspondence to: Charles Pozniak \u003C[cpozniak@hks.harvard.edu](cpozniak@hks.harvard.edu) >, Jeba Sania \u003Cjebasa[nia@hks.harvard.edu](nia@hks.harvard.edu) > .  \nSecond Workshop on Technical AI Governance Research (TAIGR)@ ICML 2026, Seoul, South Korea. 2026. Copyright 2026 by the author(s) .  \nin military, diplomatic, and geopolitical contexts (Horowitz & Kahn, 2023 ; Rivera et al., 2024 ; Lamparth et al., 2024 ; Ma et al., 2024) . Technical AI governance must catch up.  \nThe technical AI governance literature provides a strong starting vocabulary. The Reuel–Bucknall taxonomy organizes the field around six governance capacities—ASSESSMENT, ACCESS, VERIFICATION, SECURITY, OPERATIONALIZATION, and ECOSYSTEM MONITORING—as well as targets focused on DATA, COMPUTE, MODELS, and DEPLOYMENT (Reuel et al., 2025 ; Bucknall & Trager, 2023) . The taxonomy is intentionally domain-general. Our claim is that foreign policy exposes a domain-specific gap, with capacities most needed where ordinary evaluation conditions are weakest.  \nThis paper argues that foreign policy is a domain blind spot in technical AI governance. By conducting foreign policy or statecraft we mean the purposive, institutionally mediated conduct through which a political actor seeks to shape its external environment.1 This includes both the formation and implementation of external objectives: diplomatic positions, negotiations, sanctions, crisis response, and the use of force. This definition is narrower than International Relations as a whole, because it concerns the policies and decision processes of actors rather than the entire structure of the international system, but it is broader than diplomacy, featuring a broader range of instruments, such as economic and legal tools, alongside negotiation and representation (Allison & Zelikow, 1999 ; Halperin et al., 1974 ; Putnam, 1988 ; Schelling, 1960 ; Raiffa et al., 2002 ; Lax & Sebenius, 2006) .  \nWe use foreign policy and statecraft to identify a diverse deployment domain, rather than a monolithic capability tobe tested. Whether a model is “good” at foreign policy is somewhat irrelevant, instead this speaks to real-world human–AI workflow integrations in ","cbCaihikpkrdF0cj","https://ap.wps.com/l/cbCaihikpkrdF0cj","pdf",573813,17,"English","# Abstract\n# Introduction\n# Foreign Policy as a Priority Deployment Domain","[{\"question\":\"Why is foreign policy a priority domain for AI evaluation in technical AI governance research?\",\"answer\":\"Because foreign policy/statecraft is high-consequence and structurally hard to evaluate, with conditions like partial observability, unbounded action spaces, contested ground truth, and multidimensional objectives that standard benchmark practices handle poorly.\"},{\"question\":\"How does the paper define statecraft in the context of foreign policy AI systems?\",\"answer\":\"Statecraft refers to the purposive, institutionally mediated conduct through which political actors formulate and implement external objectives, including diplomacy, negotiations, sanctions, crisis response, and the use of force.\"},{\"question\":\"What is the main proposal for improving evaluation of AI systems in foreign-policy workflows?\",\"answer\":\"The paper advocates a demand-side evaluation framework that decomposes foreign-policy workflows into bounded, evaluable sub-tasks, combined by humans under institutional and strategic constraints.\"}]","The Foreign Policy AI Evaluation Gap | PDF",1789977667,43]